Automatic scoring method based on virtual experiment platform

Abstract

The invention discloses an automatic scoring method based on a virtual experiment platform, which is characterized by comprising the following steps of: 1) inputting text data, namely inputting subjective question text data, 2) preprocessing natural languages, 3) classifying question types, and 4) carrying out a scoring process. The method does not need manual scoring, and can save the scoring time, improve the scoring efficiency and improve the scoring accuracy.

Description

technical field [0001] The invention relates to the technical field of experiment teaching, in particular to an automatic scoring method based on a virtual experiment platform. Background technique [0002] Experimental instruments have always been the measurement and observation equipment often used in experimental teaching and scientific research. However, the research and development cycle of experimental instruments is long, the production process is complicated, and the cost is high. However, virtual experimental instruments designed with virtual software programming can well avoid For these shortcomings and deficiencies, the virtual experimental instrument can not only realize all the experimental functions of the experimental instrument, but also expand the function of the experimental instrument, such as adding new functions such as data storage, analysis, waveform playback, and linking to the network to realize remote control, and When the user uses the virtual expe...

AI Technical Summary

Problems solved by technology

[0004] However, there is still insufficient support for the evaluation of the design and operational capabilities of various science experiments. At the same time, with the maturity of computer simulation and virtual reality technology, the computer simulation platform for cultivating various experimental design and operational capabilities has been quite complete. , such as various simulated chemistry laboratories, simulated physics laboratories, etc., but these softwares are generally independently designed and developed by each developer, and basically do not provide functional modules for evaluation and examination, nor provide necessary interfaces for other research and development units to use Develop assessment modules based on it

[0005] The currently used virtual experiment scoring technology is mainly to add correct values ​​to the virtual simulation platform. When the experimenter uses it, he compares the data he operates with the correct values ​​to score. This scoring technology only defines the results. There is no evaluation of the experimenter's operation, it is relatively mechanized and not intelligent enough

For example, adding a shift register and a comparison function to a virtual oscilloscope based on LABVIEW directly compares whether the values ​​are the same. The method does not have any evaluation on the dynamic data of the students' operation, and cannot provide correct guidance to the students. It is relatively mechanized and not intelligent enough.

[0006] The current technology rarely uses artificial intelligence for scoring, and most of them use random selection of questions to test and score by designing a large question bank, such as computer test methods. The current method can only judge multiple-choice questions. The main subjective questions cannot be judged, and such judgments must be handed over to manual scoring

Images